Improve model card: add pipeline tag, arXiv ID, license, links, and usage instructions

README.md

@@ -6,13 +6,48 @@ tags:
 - medical
 - image-generation
 - diffusion-model
-arxiv: ...
+pipeline_tag: image-to-3d
+arxiv: 2412.13059
+license: mit
 ---
 
-# 3D MedDiffusion: A 3D Medical Diffusion Model for Controllable and High-quality Medical Image Generation
-This is the officical model repository of the paper "[**3D MedDiffusion: A 3D Medical Diffusion Model for Controllable and High-quality Medical Image Generation**](https://arxiv.org/abs/2412.13059)" 
+# 3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generation
 
-**3D MedDiffusion** is a 3D medical image synthesis framework capable of generating high-quality medical images across multiple modalities and organs.
-For more information, please refer to our [**project page**](https://shanghaitech-impact.github.io/3D-MedDiffusion.github.io/) or the [**paper**](https://arxiv.org/abs/2412.13059).
+This is the official model repository of the paper "[**3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generation**](https://arxiv.org/abs/2412.13059)".
 
-## The model is comming soon...
+**3D MedDiffusion** is a 3D medical image synthesis framework capable of generating high-quality medical images across multiple modalities and organs. It incorporates a novel, highly efficient Patch-Volume Autoencoder for latent space compression and a new noise estimator to capture both local details and global structural information during diffusion denoising. This enables the generation of fine-detailed, high-resolution images (up to 512x512x512) and ensures strong generalizability across tasks like sparse-view CT reconstruction, fast MRI reconstruction, and data augmentation.
+
+For more information, please refer to our:
+*   [**Paper (arXiv)**](https://arxiv.org/abs/2412.13059)
+*   [**Project Page**](https://shanghaitech-impact.github.io/3D-MedDiffusion/)
+*   [**GitHub Repository**](https://github.com/ShanghaiTech-IMPACT/3D-MedDiffusion)
+
+## Installation
+```bash
+## Clone this repo
+git clone https://github.com/ShanghaiTech-IMPACT/3D-MedDiffusion.git
+
+# Setup the environment
+conda create -n 3DMedDiffusion python=3.11.11
+
+conda activate 3DMedDiffusion 
+
+pip install -r requirements.txt
+```
+
+## Pretrained Models
+The pretrained checkpoint is provided [here](https://drive.google.com/drive/folders/1h1Ina5iUkjfSAyvM5rUs4n1iqg33zB-J?usp=drive_link).
+
+Please download the checkpoints and put it to `./checkpoints`.
+
+## Inference
+Make sure your GPU has at least 40 GB of memory available to run inference at all supported resolutions.
+
+**Generation using 8x downsampling**
+```python
+python evaluation/class_conditional_generation.py --AE-ckpt checkpoints/PatchVolume_8x_s2.ckpt --model-ckpt checkpoints/BiFlowNet_0453500.pt --output-dir input/your/save/dir
+```
+**Generation using 4x downsampling**
+```python
+python evaluation/class_conditional_generation_4x.py --AE-ckpt checkpoints/PatchVolume_4x_s2.ckpt --model-ckpt checkpoints/BiFlowNet_4x.pt --output-dir input/your/save/dir
+```